# Optimal Cooperative Multiplayer Learning Bandits with Noisy Rewards and No Communication

arXiv: https://arxiv.org/abs/2311.06210 · HTML: https://mlsanity.com/paper/2311.06210/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 10 Nov 2023.

## Builds on (most cited first, 13 of 13)

- [Distributed Clustering of Linear Bandits in Peer to Peer Networks](https://mlsanity.com/paper/1604.07706/) (2016)
- [SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits](https://mlsanity.com/paper/1809.08151/) (2018)
- [Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits](https://mlsanity.com/paper/1904.03293/) (2019)
- [On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2110.05707/) (2021)
- [Decentralized Multi-player Multi-armed Bandits with No Collision Information](https://mlsanity.com/paper/2003.00162/) (2020)
- [Concurrent bandits and cognitive radio networks](https://mlsanity.com/paper/1404.5421/) (2014)
- [Collaborative Top Distribution Identifications with Limited Interaction](https://mlsanity.com/paper/2004.09454/) (2020)
- [On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits](https://mlsanity.com/paper/1505.00553/) (2015)
- [Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure](https://mlsanity.com/paper/2111.00781/) (2021)
- [Online Learning for Cooperative Multi-Player Multi-Armed Bandits](https://mlsanity.com/paper/2109.03818/) (2021)
- [Decentralized Exploration in Multi-Armed Bandits -- Extended version](https://mlsanity.com/paper/1811.07763/) (2018)
- [Channel Selection for Network-assisted D2D Communication via No-Regret Bandit Learning with Calibrated Forecasting](https://mlsanity.com/paper/1404.7061/) (2014)
- [Learning Correlated Stackelberg Equilibrium in General-Sum Multi-Leader-Single-Follower Games](https://mlsanity.com/paper/2210.12470/) (2022)

## Built on by (most cited first, 8 of 8)

- [Multiplayer Information Asymmetric Bandits in Metric Spaces](https://mlsanity.com/paper/2503.08004/) (2025)
- [Cost of Structural Learning Under Censored Feedback: A Threshold-Bandit Approach](https://mlsanity.com/paper/2605.27076/) (2026)
- [Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits](https://mlsanity.com/paper/2608.10526/) (2026)
- [Robust Multi-Agent Bandits with Heavy-Tailed Rewards and Information Asymmetry](https://mlsanity.com/paper/2608.10529/) (2026)
- [DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks](https://mlsanity.com/paper/2608.11873/) (2026)
- [Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry](https://mlsanity.com/paper/2608.12753/) (2026)
- [The Price of Decentralization in Top-K Arm Identification](https://mlsanity.com/paper/2608.22120/) (2026)
- [Improved Multiplayer Bandit Algorithm for Bernoulli Rewards](https://mlsanity.com/paper/2609.26213/) (2026)

## Abstract (arXiv)

We consider a cooperative multiplayer bandit learning problem where the players are only allowed to agree on a strategy beforehand, but cannot communicate during the learning process. In this problem, each player simultaneously selects an action. Based on the actions selected by all players, the team of players receives a reward. The actions of all the players are commonly observed. However, each player receives a noisy version of the reward which cannot be shared with other players. Since players receive potentially different rewards, there is an asymmetry in the information used to select their actions. In this paper, we provide an algorithm based on upper and lower confidence bounds that the players can use to select their optimal actions despite the asymmetry in the reward information. We show that this algorithm can achieve logarithmic O(fraclog TDelta_bma) (gap-dependent) regret as well as O(√Tlog T) (gap-independent) regret. This is asymptotically optimal in T. We also show that it performs empirically better than the current state of the art algorithm for this environment.